annotate align_dbspec.py @ 2:77ddaee887a8 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
author galaxyp
date Fri, 01 Sep 2017 03:14:54 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
2
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
1 #!/usr/bin/env python
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
2 import sys
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
3 import os
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
4 import argparse
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
5 import re
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
6 from Bio import SeqIO
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
7
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
8
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
9 def create_spectra_maps(specfiles, dbfiles, frregex, firstfr):
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
10 """Output something like
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
11 {'fr01', 'fr04'} # Normal filename set
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
12 and
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
13 {'fr03': ['fr02', 'fr03']} # pool definition
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
14 and
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
15 {'fr04': 'fr04', 'fr04b': 'fr04'} # rerun fraction, rerun may also be pool
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
16 """
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
17 specrange = get_fn_fractionmap(specfiles, frregex)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
18 to_pool = []
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
19 poolmap, rerun_map, normal_fns = {}, [], set()
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
20 for i in range(0, len(dbfiles)):
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
21 num = i + firstfr
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
22 if num not in specrange:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
23 to_pool.append(i)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
24 elif to_pool and num in specrange:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
25 to_pool.append(i)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
26 poolmap[specrange[num][0]] = to_pool
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
27 to_pool = []
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
28 if not to_pool and specrange[num][0] in poolmap:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
29 if poolmap[specrange[num][0]][-1] != i:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
30 normal_fns.add((dbfiles[num - 1],
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
31 specfiles[specrange[num][0]]))
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
32 elif not to_pool:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
33 normal_fns.add((dbfiles[num - 1], specfiles[specrange[num][0]]))
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
34 for num in sorted(specrange.keys()):
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
35 if len(specrange[num]) > 1:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
36 rerun_map.append(specrange[num])
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
37 return normal_fns, rerun_map, poolmap
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
38
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
39
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
40 def get_fn_fractionmap(files, frregex):
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
41 fnfrmap = {}
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
42 for f_ix, fn in enumerate(files):
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
43 fnum = int(re.sub(frregex, '\\1', fn))
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
44 try:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
45 fnfrmap[fnum].append(f_ix)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
46 except KeyError:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
47 fnfrmap[fnum] = [f_ix]
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
48 return fnfrmap
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
49
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
50
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
51 def pool_fasta_files(poolfiles):
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
52 acc_seq = {}
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
53 for fr in poolfiles:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
54 for seq in SeqIO.parse(fr, 'fasta'):
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
55 sequence = str(seq.seq.upper())
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
56 try:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
57 if sequence in acc_seq[seq.id]:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
58 continue
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
59 except KeyError:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
60 acc_seq[seq.id] = {sequence: 1}
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
61 yield seq
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
62 else:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
63 acc_seq[seq.id][sequence] = 1
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
64 yield seq
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
65
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
66
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
67 def write_pooled_fasta(poolmap, specnames, dbfiles):
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
68 """Runs through poolmap and pooles output files, filtering out
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
69 duplicates"""
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
70 for outfr, infrs in poolmap.items():
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
71 outfn = os.path.join('aligned_out', os.path.basename(specnames[outfr]))
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
72 print('Pooling FASTA files {} - {} into: {}'.format(
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
73 dbfiles[infrs[0]], dbfiles[infrs[-1]], outfn))
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
74 with open(outfn, 'w') as fp:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
75 SeqIO.write(pool_fasta_files([dbfiles[x] for x in infrs]), fp,
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
76 'fasta')
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
77
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
78
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
79 def write_nonpooled_fasta(fractions):
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
80 """Symlinks nonpooled db files"""
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
81 print('Symlinking non-pooled non-rerun files',
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
82 [(fr[0], os.path.join('aligned_out', os.path.basename(fr[1])))
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
83 for fr in fractions])
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
84 [os.symlink(fr[0], os.path.join('aligned_out', os.path.basename(fr[1])))
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
85 for fr in fractions]
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
86
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
87
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
88 def copy_rerun_fasta(rerun_map, specnames):
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
89 for dst_indices in rerun_map:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
90 src = os.path.join(specnames[dst_indices[0]])
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
91 for outfn in [specnames[x] for x in dst_indices[1:]]:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
92 print('Symlinking {} to {}'.format(src, outfn))
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
93 os.symlink(src, os.path.join('aligned_out', outfn))
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
94
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
95
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
96 def main():
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
97 args = parse_commandline()
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
98 with open(args.spectranames) as fp:
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
99 spectranames = [x.strip() for x in fp.read().strip().split('\n')]
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
100 vanilla_fr, rerun_map, poolmap = create_spectra_maps(spectranames,
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
101 args.dbfiles,
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
102 args.frspecregex,
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
103 args.firstfr)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
104 write_pooled_fasta(poolmap, spectranames, args.dbfiles)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
105 write_nonpooled_fasta(vanilla_fr)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
106 copy_rerun_fasta(rerun_map, spectranames)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
107
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
108
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
109 def parse_commandline():
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
110 parser = argparse.ArgumentParser(
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
111 formatter_class=argparse.RawTextHelpFormatter)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
112 parser.add_argument('--specnames', dest='spectranames', help='File '
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
113 'containing spectra filenames with fractions. '
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
114 'Test data example illustrates reruns (fr03b, 09b) and'
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
115 ' pooled samples (fr05-09 are inside fr09 and fr09b).',
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
116 required=True)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
117 parser.add_argument('--dbfiles', dest='dbfiles', help='FASTA db files',
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
118 nargs='+', required=True)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
119 parser.add_argument('--frspec', dest='frspecregex', help='Fraction regex '
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
120 'to detect spectra fraction numbers', required=True)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
121 parser.add_argument('--firstfr', dest='firstfr', help='First fraction nr',
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
122 type=int, required=True)
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
123 return parser.parse_args(sys.argv[1:])
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
124
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
125
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
126 if __name__ == '__main__':
77ddaee887a8 planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/pi_db_tools commit 71a4265d11aef48342142b8cf2caa86f79f9a554
galaxyp
parents:
diff changeset
127 main()